Customer Lifetime Value (LTV) prediction, a central problem in modern marketing, is characterized by a unique zero-inflated and long-tail data distribution. This distribution presents two fundamental challenges: (1) the vast majority of low-to-medium value users numerically overwhelm the small but critically important segment of high-value ''whale'' users, and (2) significant value heterogeneity exists even within the low-to-medium value user base. Common approaches either rely on rigid statistical assumptions or attempt to decouple ranking and regression using ordered buckets; however, they often enforce ordinality through loss-based constraints rather than inherent architectural design, failing to balance global accuracy with high-value precision. To address this gap, we propose Conditional Cascaded Ordinal-Residual Networks (CC-OR-Net), a novel unified framework that achieves a more robust decoupling through structural decomposition, where ranking is architecturally guaranteed. CC-OR-Net integrates three specialized components: a structural ordinal decomposition module for robust ranking, an intra-bucket residual module for fine-grained regression, and a targeted high-value augmentation module for precision on top-tier users. Evaluated on real-world datasets with over 300M users, CC-OR-Net achieves a superior trade-off across all key business metrics, outperforming state-of-the-art methods in creating a holistic and commercially valuable LTV prediction solution.
论文检索
输入标题、作者或关键词，从 17,487 篇学术成果中精准定位
Sequential recommender systems play a vital role in alleviating the challenge of information overload. Although contrastive learning has been increasingly adopted in sequential recommendation to enhance model performance, most existing approaches rely on predefined data augmentation strategies—such as random noise injection or neuron dropout—to generate contrasting views. These strategies, however, often overlook the inherent semantic similarity between the original sequence and its augmented views, which can inadvertently distort user intent and compromise recommendation accuracy. To address this issue, we propose an Adaptive Contrastive Learning framework for Sequential Recommendation (ACLSRec), which incorporates learnable perturbation and restoration networks for adaptive augmentation. The framework dynamically perturbs and restores user representations, thereby ensuring semantic consistency across augmented views and effectively capturing evolving user interest patterns through contrastive learning. Extensive experiments on real-world datasets demonstrate that ACLSRec achieves superior recommendation accuracy compared to several competitive baselines. This work not only establishes a new baseline for sequential recommendation but also paves the way for developing more robust and adaptive contrastive learning frameworks in recommender systems. The source code is available at https://github.com/xiaomizhou778/ACLSRec.
Despite the success of Graph Neural Networks (GNNs) in modeling recommender systems as bipartite graphs, their ability to capture diverse user-item relations remains limited by the sparsity of observed interactions, which fails to reveal the underlying latent intents. We propose IACLR (Intention Alignment via Contrastive Learning for bipartite graph Recommendation), a framework that constructs an Intent-Graph by augmenting the bipartite recommendation graphs with an implicit intent layer. Instead of relying solely on observed edges, IACLR introduces a set of intent nodes that bridge users and items through shared semantic and behavioral patterns. These nodes are used to construct an Intent-Graph, where they act as both intermediaries that enrich structural connectivity and global anchors that summarize latent user interests. Within this graph, IACLR performs contrastive alignment across multiple data views and enforces consistency among users, intents, and items, thereby enhancing robustness under data sparsity. Experiments on benchmark datasets (e.g., Amazon-books and Yelp) demonstrate that IACLR consistently outperforms strong graph-based, revealing its effectiveness in capturing fine-grained user–item relationships and integrating multi-faceted signals. The framework is applicable to various recommendation scenarios, including academic paper recommendations, e-commerce, and content platforms.
Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory—particularly in complex, long-term Web-based services such as online emotional support. However, existing long-term dialogue benchmarks primarily focus on static and explicit fact retrieval, failing to evaluate agents in these critical scenarios where user information is dispersed, implicit, and continuously evolving. To address this gap, we introduce ES-MemEval, a comprehensive benchmark that systematically evaluates five core memory capabilities—information extraction, temporal reasoning, conflict detection, abstention, and user modeling—in long-term emotional support scenarios, covering question answering, summarization, and dialogue generation tasks. To support the benchmark, we also propose EvoEmo, the first multi-session dataset for personalized long-term emotional support scenarios, capturing fragmented, implicit user disclosures and evolving user states. Extensive experiments on open-source long-context, commercial, and retrieval-augmented (RAG) LLMs reveal that explicit long-term memory is essential to reduce hallucinations and enable effective personalization. At the same time, RAG enhances factual consistency but struggles with temporal dynamics and evolving user states. These findings highlight both the potential and limitations of current paradigms, encouraging the development of more robust memory–retrieval integration in long-term personalized dialogue systems.
Implicit feedback is central to modern recommender systems but is inherently noisy, often impairing model training and degrading user experience. At scale, such noise can mislead learning processes, reducing both recommendation accuracy and platform value. Existing denoising strategies typically overlook the entity-specific nature of noise while introducing high computational costs and complex hyperparameter tuning. To address these challenges, we propose EARD (Entity-Aware Reliability-Driven Denoising), a lightweight framework that shifts the focus from interaction-level signals to entity-level reliability. Motivated by the empirical observation that training loss correlates with noise, EARD quantifies user and item reliability via their average training losses as a proxy for reputation, and integrates these entity-level factors with interaction-level confidence. The framework is model-agnostic, computationally efficient, and requires only two intuitive hyperparameters. Extensive experiments across multiple datasets and backbone models demonstrate that EARD yields substantial improvements over state-of-the-art baselines (e.g., up to 27.01% gain in NDCG@50), while incurring negligible additional computational cost. Comprehensive ablation studies and mechanism analyses further confirm EARD's robustness to hyperparameter choices and its practical scalability. These results highlight the importance of entity-aware reliability modeling for denoising implicit feedback and pave the way for more robust recommendation research.
Web-based participatory urban sensing has emerged as a vital approach for modern urban management by leveraging mobile individuals as distributed sensors. However, existing urban sensing systems struggle with limited generalization across diverse urban scenarios and poor interpretability in decision-making. In this work, we introduce AgentSense, a hybrid, training-free framework that integrates large language models (LLMs) into participatory urban sensing through a multi-agent refinement system. AgentSense initially employs a classical planner to generate baseline solutions and then iteratively refines them to adapt sensing task assignments to dynamic urban conditions and heterogeneous worker preferences, while producing natural language explanations that enhance transparency and trust. Extensive experiments across two large-scale mobility datasets and seven types of dynamic disturbances demonstrate that AgentSense offers distinct advantages in adaptivity and explainability over traditional methods. Furthermore, compared to single-agent LLM baselines, our approach outperforms in both performance and robustness, while delivering more reasonable and transparent explanations. These results position AgentSense as a significant advancement towards deploying adaptive and explainable urban sensing systems on the web.
Large Language Models (LLMs) are increasingly deployed on edge devices to address privacy and latency concerns in modern Web applications. While numerous studies focus on inference frameworks, the critical problem of tuning runtime configurations remains largely underexplored. This endeavor is particularly challenging on edge devices due to severe budget limitations and the dynamic variability of system resources. To address these challenges, we draw upon key insights regarding parameter sensitivity, configuration transferability, and rank stability to propose LaTune, a lightweight and adaptive tuning framework. LaTune is designed to efficiently find optimal runtime configurations by incorporating three complementary components: parameter selection to focus on the most impactful parameters, knowledge transfer to leverage historical data for accelerated search, and two-stage optimization to dynamically select the best configuration based on real-time resource constraints. Experiments across four edge devices and LLMs show that LaTune achieves up to 3.93x higher hypervolume and 6.90x throughput gains over baselines. It accelerates tuning efficiency by 2-3x, converging within 10-20 iterations, and ensures robust execution under heavy contention where static methods fail. Our code is open-sourced at https://github.com/pkuaiweb/LaTune.
Adaptive traffic signal control (ATSC) is essential for mitigating urban congestion in modern smart cities, where traffic infrastructure is evolving into interconnected Web-of-Things (WoT) environments with thousands of sensing-and-control nodes. However, existing methods face a critical scalability-coordination tradeoff: centralized approaches optimize global objectives but become computationally intractable at city scale, while decentralized multi-agent methods scale efficiently yet lack network-level coherence, resulting in suboptimal performance. In this paper, we present HALO, a hierarchical reinforcement learning framework that addresses this tradeoff for large-scale ATSC. HALO decouples decision-making into two levels: a high-level global guidance policy employs Transformer-LSTM encoders to model spatio-temporal dependencies across the entire network and broadcast compact guidance signals, while low-level local intersection policies execute decentralized control conditioned on both local observations and global context. To ensure better alignment of global-local objectives, we introduce an adversarial goal-setting mechanism where the global policy proposes challenging-yet-feasible network-level targets that local policies are trained to surpass, fostering robust coordination. We evaluate HALO extensively on multiple standard benchmarks, and a newly constructed large-scale Manhattan-like network with 2,668 intersections under real-world traffic patterns, including peak transitions, adverse weather and holiday surges. Results demonstrate HALO shows competitive performance and becomes increasingly dominant as network complexity grows across small-scale benchmarks, while delivering the strongest performance in all large-scale regimes, offering up to 6.8% lower average travel time and 5.0% lower average delay than the best state-of-the-art.
Federated domain generalization (FDG) for time-series classification (TSC) poses a critical challenge for modern intelligent web services, which rely on edge-collected time-series signals from diverse mobile applications and web devices (e.g., wearables sensors) to support decision-making. The source heterogeneity and temporal dynamics give rise to out-of-distribution (OOD) patterns, which hinder the model's ability to generalize to previously unseen users and devices. In this work, we propose Federated Generalization via Diversity Generation (FedDiG), a diffusion-based FDG framework that captures intra-client distribution shifts from a frequency-domain perspective and employs cross-frequency sampling to synthesize time-series data with diverse spectral patterns. Specifically, FedDiG first performs frequency-proxy representation learning on clients to serve as diffusion conditions. The server then aggregates client-side frequency proxies to construct a global proxy pool and applies class-wise mixup to create novel frequency features. These features guide a global diffusion model to produce diverse data, enabling the simulation of previously unseen patterns and thereby enhancing model training. Extensive experiments on four cross-domain time-series benchmarks demonstrate that FedDiG significantly outperforms state-of-the-art federated learning and FDG baselines, particularly under small-data regimes and large-scale client scenarios, achieving robust generalization to unseen domains in federated settings. This work bridges distribution-diversity synthesis and FDG for time-series to support robust, scalable web applications fed by edge-collected signals, delivering web-scale generalization across heterogeneous web, mobile, and IoT clients.
Disaggregated Memory Systems (DMS) hold substantial potential for cloud datacenters but face critical deployment barriers in multi-tenant RDMA environments. Existing DMS designs rely on idealized assumptions-overlooking interference from co-located RDMA applications, oversimplifying fabric topology considerations, and lacking elastic service-level objectives (SLOs) guarantees-resulting in performance degradation and resource inefficiency. To bridge these gaps, we introduce Wiseswap, an elastic, datacenter network-aware DMS that delivers robust memory disaggregation for multi-tenant clouds through three key innovations: (1) Preemption-enabled isolation: A low-overhead kernel mechanism utilizes WAIT/ENABLE RDMA primitives to prioritize latency-critical swap operations over user-space RDMA flows, maintaining tenant fairness; (2) Adaptive fabric path selection: In-kernel telemetry dynamically probes latency and routes memory traffic through uncongested paths, mitigating interference from elephant flows; (3) Feedback-directed autoscaling: Fine-grained optimization of DMS-specific parameters-dynamically optimizes resource allocation under fluctuating workloads, guaranteeing stringent SLOs while minimizing resource overhead. Evaluations demonstrate that Wiseswap improves throughput by 1.3-2.4x and reduces tail latency by 57-73% under contention compared to state-of-the-art solutions, while consistently meeting strict SLO targets.
Trace analysis is essential for understanding system behaviors, detecting anomalies, and diagnosing faults in complex microservice-based web applications. Existing trace analysis approaches face several challenges in industrial microservice-based systems, including high manual overhead, limited functionality, unfriendly interaction mechanisms, and difficulties in deployment and integration. The strong capabilities of large language models (LLMs) in natural language understanding, reasoning, and multi-task generalization provide new opportunities for a more intelligent and flexible trace analysis approach. However, the trace analysis capabilities of LLMs remain underexplored and underdeveloped. To bridge this gap, we conduct the first comprehensive evaluation on the trace analysis capabilities of LLMs. In particular, we construct the first instruction&response benchmark dataset for trace analysis, named TraceBench. It involves a wide range of trace analysis tasks, allowing us to systematically evaluate the capabilities of LLMs in this area. Experimental results show that LLMs have potential in handling trace analysis tasks, but there leaves room for improvement. To this end, we propose TraceLLM, an approach that significantly enhances the capabilities of LLMs via fine-tuning, outperforming the open-source LLMs by 34.77% on average in terms of accuracy, and outperforming the closed-source model by 21.66% in the best case. The generalization and robustness of TraceLLM are also confirmed in our experiments. To the best of our knowledge, TraceLLM is the first LLM which is specialized for handling various types of trace analysis tasks. This work provides a foundation for future research to further explore the trace analysis capabilities of LLMs.
Virtual private clouds (VPCs) play a critical role in providing secure and isolated network environments for web services. However, with the growing number and size of VPCs, efficiently delivering control messages from the control plane to the data plane has become a major concern for cloud vendors. Existing end-to-end transmission solutions (e.g., RPC) will result in substantial overhead in the control plane, while message-oriented middleware-based solutions (e.g., message queue) will lead to high data plane overhead. To address this issue, we design Meteor, a high-performance control message delivery system for large-scale clouds. Specifically, Meteor combines an RPC path with a message queue (MQ) path and employs an auto dual-path switching mechanism to minimize the message delivery latency. Additionally, we propose a VPC-based message delivery and filtering scheme for the MQ path to reduce data plane overhead. We also design a delivery robustness guarantee mechanism to ensure the reachability and consistency of control messages. Meteor has been thoroughly tested with up to 100k container instances. Evaluation results show that Meteor decreases the message delivery latency by 48.8% and reduces the overhead by about 50% in real-world scenarios, compared with state-of-the-art solutions.
The World Wide Web increasingly relies on intelligent services that require accurate time series forecasting, from urban mobility platforms to adaptive web-based decision systems. In practice, building effective forecasting models typically requires abundant high-quality data, which may not always be available in all cities due to sensing limitations or data sparsity. To address this challenge, transfer learning methods aim to transfer knowledge from data-rich source cities to data-scarce target cities. However, source and target data distributions are often not identical: while some patterns from source cities may be beneficial, others can be irrelevant or even misleading. Existing transfer learning methods generally train the target model using all available source data without explicitly distinguishing between useful and non-useful knowledge, which may hinder performance. In this work, we propose xRAG4TS, a novel framework that integrates Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) for cross-city time series forecasting. xRAG4TS introduces a Cross-City Selective Retriever Module that filters semantically relevant historical patterns and documents from data-rich source cities, and incorporates them as structured prompts in an LLM Inference Module to guide forecasting in data-scarce target cities. By enabling selective, interpretable, and context-aware knowledge transfer, our method enhances robustness and scalability in web-oriented spatio-temporal applications. Extensive experiments on real-world cross-city datasets demonstrate that xRAG4TS significantly outperforms state-of-the-art baselines, highlighting its potential for powering adaptive and trustworthy web services under severe data scarcity.
Online hate on social media ranges from overt slurs and threats (hard hate speech ) to soft hate speech: discourse that appears reasonable on the surface but uses framing and value-based arguments to steer audiences toward blaming or excluding a target group. We hypothesize that current moderation systems, largely optimized for surface toxicity cues, are not robust to this reasoning-driven hostility, yet existing benchmarks do not measure this gap systematically. We introduce SoftHateBench, a generative benchmark that produces soft-hate variants while preserving the underlying hostile standpoint. To generate soft hate, we integrate the Argumentum Model of Topics (AMT) and Relevance Theory (RT) in a unified framework: AMT provides the backbone argument structure for rewriting an explicit hateful standpoint into a seemingly neutral discussion while preserving the stance, and RT guides generation to keep the AMT chain logically coherent. The benchmark spans 7 sociocultural domains and 28 target groups, comprising 4,745 soft-hate instances. Evaluations across encoder-based detectors, general-purpose LLMs, and safety models show a consistent drop from hard to soft tiers: systems that detect explicit hostility often fail when the same stance is conveyed through subtle, reasoning-based language. Disclaimer. Contains offensive examples used solely for research.
Restaurants, as small hospitality businesses, are inherently vulnerable, making accurate survival prediction crucial. Previous studies have demonstrated the significance of user reviews and incorporated diverse review?derived factors, yet they have largely overlooked the large?scale network formed by user–restaurant interactions. How restaurant survival is influenced by the review network remains insufficiently explored. To fill this gap, leveraging network embeddedness theory, we statistically analyze the impact of two dimensions of embeddedness, structural and positional, on each restaurant's survival. Utilizing two real-world review datasets, the newly curated OpenRice and the well-established Yelp, our results reveal that a restaurant's network embeddedness and its temporal evolution positively correlate with its survival. Building on this insight, we propose a Dynamic Embeddedness-aware Graph Neural Network, DyE-GNN, for restaurant survival prediction. DyE-GNN not only explicitly integrates network embeddedness theory to guide the model design but also leverages domain knowledge to enable robust adaptability. Extensive experiments on both datasets confirm the superiority of DyE-GNN, underscoring the importance of network embeddedness attention, temporal dynamics, and survival knowledge of peer restaurants. Visualizations further demonstrate that network embeddedness facilitates the identification of at-risk restaurants at the network margin.
Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persistently develop evasive perturbations to disguise toxic content and evade detectors. Traditional detectors or methods are static over time and are inadequate in addressing these evolving evasion tactics. Thus, continual learning emerges as a logical approach to dynamically update detection ability against evolving perturbations. Nevertheless, disparities across perturbations hinder the detector's continual learning on perturbed text. More importantly, perturbation-induced noises distort semantics to degrade comprehension and also impair critical feature learning to render detection sensitive to perturbations. These amplify the challenge of continual learning against evolving perturbations. In this work, we present ContiGuard, the first framework tailored for continual learning of the detector on time-evolving perturbed text (termed continual toxicity detection) to enable the detector to continually update capability and maintain sustained resilience against evolving perturbations. Specifically, to boost the comprehension, we present an LLM powered semantic enriching strategy, where we dynamically incorporate possible meaning and toxicity-related clues excavated by LLM into the perturbed text to improve the comprehension. To mitigate non-critical features and amplify critical ones, we propose a discriminability driven feature learning strategy, where we strengthen discriminative features while suppressing the less-discriminative ones to shape a robust classification boundary for detection. Additionally, we introduce a historical capability replay strategy to preserve previously learned features via feature alignment to alleviate capability forgetting. To the best of our knowledge, this work is the first study on continual toxicity detection against time-evolving evasive perturbed text. Extensive experiments prove the superior performance of ContiGuard over both existing detectors and continual methods. Code and dataset are available at https://github.com/khk-abc/ContiGuard. Warning: This paper contains discussions of harmful content that may be disturbing to some readers.
The widespread use of social-media graphs has provided a convenient channel for rumor propagation. Rapid localization of rumor sources is therefore crucial for mitigating diffusion and enabling punitive countermeasures. Source Localization (SL) aims to identify the origin nodes given partial infection observations. Although deep-learning-based SL approaches outperform traditional estimators, three fundamental limitations remain: (i) Model Complexity —existing methods enrich node embeddings with cascades of auxiliary features, yielding high-capacity but excessively complex representations, leading to an exponential increase in the number of model parameters; (ii) Annotation gap —to overcome the scarcity of real-world misinformation cascades, current pipelines repeatedly simulate diffusion from a fixed seed, eroding robustness on true, few-shot outbreaks; and (iii) Computational bottleneck —full-model retraining or recurrent cascade simulation is required for every new task, which disqualifies the solutions from real-time deployment. Inspired by the success of prompt learning in NLP and graph learning, we propose LAPS, a Lightweight privilege-Allocation Prompting framework for Source localization. LAPS first trims parameter explosion and data scarcity by pre-training a graph-level source region classifier on adaptive subgraphs with source-prior diffusion data. It then enables few-shot SL via a privilege-allocation prompt module that updates <1% of all the parameters, avoiding model retraining to facilitate efficiency. Extensive experiments on five real-world networks demonstrate the effectiveness and efficiency of our prompt-based framework on few-shot source localization task.
Detecting social bots is critical to ensuring the security of online discourse and maintaining trust in social networks. Early feature-based and text-based methods often fail against bots that mimic human behavior, and graph-based approaches have emerged to better exploit structural signals. However, most existing Graph Neural Networks (GNNs) still focus on pairwise connections, overlooking higher-order relational patterns, and their multi-relation fusion strategies are typically simplistic, ignoring dependencies between relations and user-specific preferences. To overcome these limitations, we propose MPS-Bot, a model that integrates higher-order structure modeling with user-specific cross-relation dependency learning. MPS-Bot introduces a simplex convolutional layer that leverages simplexes derived from network structures to capture group coordination patterns beyond pairwise connections. In addition, a cross-relation dependency attention mechanism adaptively fuses relation-specific representations according to each user's relational preferences, leading to more discriminative and robust multi-relation representations. Extensive experiments on two widely used Twitter bot detection benchmarks, MGTAB and TwiBot-22, show that MPS-Bot generally outperforms state-of-the-art baselines. These findings highlight the effectiveness of higher-dimensional message passing over simplexes as a powerful approach to unmasking bots in social networks.
Abnormal user detection has been a critical and widely studied research problem in social networks since these users can create significant risks to platform security and privacy leakage. Currently, graph-based models are commonly used for exploring the structured social network data and temporally dynamic user interactions, leading to significant advances in dynamic heterogeneous graph-based abnormal user detection. However, most existing approaches are correlation-driven and lack the ability to separate stable patterns from transient noise. Furthermore, these methods are highly dependent on inherent labels and fail to detect common few-shot anomalies in social networks. To address these issues, we propose CIFAD, a Causal-Invariant Few-shot Anomaly Detection method that improves few-shot anomaly detection with an active annotation strategy. Specifically, CIFAD first integrates a sparse lagged attention encoder to model multi-relational temporal interactions. Furthermore, it introduces causal-invariant subspace decomposition to disentangle stable causal signals from dynamic environmental noise and improve generalization. Finally, it designs an active annotation strategy based on influence functions and coverage optimization to maximize the utility of limited labels in a closed-loop process. Extensive experiments on multiple real-world social network datasets demonstrate that our method achieves higher accuracy than state-of-the-art methods, validating its robustness in abnormal user detection for social networks.
Graph Neural Networks (GNNs) demonstrate promising performance in data mining yet exhibit inherent vulnerabilities to adversarial attacks. Even imperceptible perturbations degrade model performance, seriously hindering the application of GNNs in reality. In recent years, adversarial defense methods based on model architecture have gained attention for their effectiveness. However, they exhibit limited effectiveness against emerging black-box influence maximization attacks (IMAs), which aim to maximize the spread of feature perturbations through a group of influential nodes. This may leave a potential risk in real-world applications. To address this issue, we propose a Graph Adversarial Defense method based on the Hilbert-Schmidt Independence Criterion (HSIC-GAD). Specifically, the proposed method leverages hidden representations to capture the dependence between preprocessed node features and label information. On this basis, we design a regularizer that simultaneously preserves the most relevant information for downstream tasks while filtering out adversarial perturbations from the input data. A simple theoretical analysis shows that the HSIC regularizer can reduce the sensitivity of the model to adversarial inputs. Additionally, it exhibits strong universality, consistently enhancing the adversarial robustness of diverse models. Extensive experiments on real-world datasets demonstrate that HSIC-GAD outperforms state-of-the-art defense methods against IMAs.